FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319963669> ?p ?o ?g. }

• W4319963669 endingPage "33" @default.
• W4319963669 startingPage "1" @default.
• W4319963669 abstract "Recently, there has been significant growth of interest in applying software engineering techniques for the quality assurance of deep learning (DL) systems. One popular direction is DL testing—that is, given a property of test, defects of DL systems are found either by fuzzing or guided search with the help of certain testing metrics. However, recent studies have revealed that the neuron coverage metrics, which are commonly used by most existing DL testing approaches, are not necessarily correlated with model quality (e.g., robustness, the most studied model property), and are also not an effective measurement on the confidence of the model quality after testing. In this work, we address this gap by proposing a novel testing framework called QuoTe (i.e., Qu ality- o riented Te sting). A key part of QuoTe is a quantitative measurement on (1) the value of each test case in enhancing the model property of interest (often via retraining) and (2) the convergence quality of the model property improvement. QuoTe utilizes the proposed metric to automatically select or generate valuable test cases for improving model quality. The proposed metric is also a lightweight yet strong indicator of how well the improvement converged. Extensive experiments on both image and tabular datasets with a variety of model architectures confirm the effectiveness and efficiency of QuoTe in improving DL model quality—that is, robustness and fairness. As a generic quality-oriented testing framework, future adaptations can be made to other domains (e.g., text) as well as other model properties." @default.
• W4319963669 created "2023-02-11" @default.
• W4319963669 creator A5001395097 @default.
• W4319963669 creator A5011847644 @default.
• W4319963669 creator A5040919350 @default.
• W4319963669 creator A5052794441 @default.
• W4319963669 creator A5068084440 @default.
• W4319963669 creator A5068911982 @default.
• W4319963669 creator A5078711649 @default.
• W4319963669 date "2023-07-22" @default.
• W4319963669 modified "2023-09-26" @default.
• W4319963669 title "<scp>QuoTe</scp> : Quality-oriented Testing for Deep Learning Systems" @default.
• W4319963669 cites W1892947258 @default.
• W4319963669 cites W1965194038 @default.
• W4319963669 cites W2051846789 @default.
• W4319963669 cites W2065948900 @default.
• W4319963669 cites W2112796928 @default.
• W4319963669 cites W2130486630 @default.
• W4319963669 cites W2139137304 @default.
• W4319963669 cites W2162739315 @default.
• W4319963669 cites W2180612164 @default.
• W4319963669 cites W2194775991 @default.
• W4319963669 cites W2325939864 @default.
• W4319963669 cites W2543296129 @default.
• W4319963669 cites W2616028256 @default.
• W4319963669 cites W2730550703 @default.
• W4319963669 cites W2793350103 @default.
• W4319963669 cites W2795283266 @default.
• W4319963669 cites W2809701591 @default.
• W4319963669 cites W2884801476 @default.
• W4319963669 cites W2886368623 @default.
• W4319963669 cites W2888824816 @default.
• W4319963669 cites W2900153411 @default.
• W4319963669 cites W2919115771 @default.
• W4319963669 cites W2924551358 @default.
• W4319963669 cites W2957905354 @default.
• W4319963669 cites W2962793481 @default.
• W4319963669 cites W2963308851 @default.
• W4319963669 cites W2963327228 @default.
• W4319963669 cites W2963857521 @default.
• W4319963669 cites W2963913218 @default.
• W4319963669 cites W2967682612 @default.
• W4319963669 cites W2974147052 @default.
• W4319963669 cites W2982232682 @default.
• W4319963669 cites W3002398329 @default.
• W4319963669 cites W3035447895 @default.
• W4319963669 cites W3042703469 @default.
• W4319963669 cites W3043716470 @default.
• W4319963669 cites W3087720408 @default.
• W4319963669 cites W3090643686 @default.
• W4319963669 cites W3099444373 @default.
• W4319963669 cites W3105599650 @default.
• W4319963669 cites W3120485916 @default.
• W4319963669 cites W3120991880 @default.
• W4319963669 cites W3124058431 @default.
• W4319963669 cites W4285490447 @default.
• W4319963669 cites W4291213652 @default.
• W4319963669 doi "https://doi.org/10.1145/3582573" @default.
• W4319963669 hasPublicationYear "2023" @default.
• W4319963669 type Work @default.
• W4319963669 citedByCount "0" @default.
• W4319963669 crossrefType "journal-article" @default.
• W4319963669 hasAuthorship W4319963669A5001395097 @default.
• W4319963669 hasAuthorship W4319963669A5011847644 @default.
• W4319963669 hasAuthorship W4319963669A5040919350 @default.
• W4319963669 hasAuthorship W4319963669A5052794441 @default.
• W4319963669 hasAuthorship W4319963669A5068084440 @default.
• W4319963669 hasAuthorship W4319963669A5068911982 @default.
• W4319963669 hasAuthorship W4319963669A5078711649 @default.
• W4319963669 hasBestOaLocation W43199636691 @default.
• W4319963669 hasConcept C104317684 @default.
• W4319963669 hasConcept C106436119 @default.
• W4319963669 hasConcept C108913964 @default.
• W4319963669 hasConcept C111472728 @default.
• W4319963669 hasConcept C111919701 @default.
• W4319963669 hasConcept C119857082 @default.
• W4319963669 hasConcept C124101348 @default.
• W4319963669 hasConcept C127413603 @default.
• W4319963669 hasConcept C128942645 @default.
• W4319963669 hasConcept C136264566 @default.
• W4319963669 hasConcept C137726913 @default.
• W4319963669 hasConcept C138885662 @default.
• W4319963669 hasConcept C149091818 @default.
• W4319963669 hasConcept C152877465 @default.
• W4319963669 hasConcept C154945302 @default.
• W4319963669 hasConcept C162324750 @default.
• W4319963669 hasConcept C162443782 @default.
• W4319963669 hasConcept C176217482 @default.
• W4319963669 hasConcept C178059732 @default.
• W4319963669 hasConcept C185592680 @default.
• W4319963669 hasConcept C186846655 @default.
• W4319963669 hasConcept C188087704 @default.
• W4319963669 hasConcept C189950617 @default.
• W4319963669 hasConcept C199360897 @default.
• W4319963669 hasConcept C200601418 @default.
• W4319963669 hasConcept C21547014 @default.
• W4319963669 hasConcept C2777904410 @default.
• W4319963669 hasConcept C2779530757 @default.

• next